Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vastaan
    -0.66
     informée
    -0.62
    VersionUID
    -0.61
     aikana
    -0.56
    出版年
    -0.53
     utafitiHapana
    -0.52
    })->
    -0.52
    醐
    -0.51
    inobu
    -0.51
     feroit
    -0.51
    POSITIVE LOGITS
     means
    0.89
     MEANS
    0.65
     reason
    0.64
    '
    0.63
    means
    0.63
    Means
    0.62
     virtue
    0.62
     Means
    0.61
     removal
    0.59
     reasons
    0.58
    Act Density 0.013%

    No Known Activations